mradermacher/UnifiedReward-Flex-qwen3vl-4b-i1-GGUF
Full fine-tune (fewer layers) vs CodeGoat24/UnifiedReward-Flex-qwen3vl-4b. mradermacher/UnifiedReward-Flex-qwen3vl-4b-i1-GGUF matches part of CodeGoat24/UnifiedReward-Flex-qwen3vl-4b (398 of its 714 tensors; the rest of CodeGoat24/UnifiedReward-Flex-qwen3vl-4b has no counterpart). On the shared part: mradermacher/UnifiedReward-Flex-qwen3vl-4b-i1-GGUF is a GGUF (Q6_K) of different weights. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 1/1, Norms 126/145, MLP 108/108, Attention 144/144